Updated 2mo ago
by 6987886-ux
3s-codex-workflow
Three lightweight Codex workflow skills for goal clarity, evidence-based review, and safe public research.
98 GitHub stars (98)
Steady at 98 stars — no new stars in the 16 days since Sep 30.
- 3 skills (3 skills found in its SKILL.md files)
- 0 forks (0 forks)
- 2mo ago last update (Last updated 2mo ago)
Install
Skills CLI
npx skills add 6987886-ux/3s-codex-workflow
Asks which skills and agents to install. Just one: npx skills add 6987886-ux/3s-codex-workflow --skill codex-project-reviewer — add -g for every project.
Claude Code
git clone https://github.com/6987886-ux/3s-codex-workflowcp -r "3s-codex-workflow/skills/codex-project-reviewer" ~/.claude/skills/
Copies the codex-project-reviewer skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add 6987886-ux/3s-codex-workflow
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
codex-project-reviewer
Perform an independent, read-only review of a coding project's Goal, Scope, Git baseline, implementation, tests, gate, uncommitted changes, and completion claim. Use before acceptance, merge, release, or handoff when a claim must be checked against repository evidence.
skills/codex-project-reviewer/SKILL.md on GitHub (opens in a new tab) -
3s-product-goal-clarifier
Turn an ambiguous product idea into an explicit Goal, Scope, Constraints, Success Criteria, Non-goals, and Milestones before implementation. Use when a coding agent needs an approved, testable product target and the requested outcome or boundaries are still unclear.
skills/product-goal-clarifier/SKILL.md on GitHub (opens in a new tab) -
safe-public-research
Research GitHub projects, competitors, open-source software, markets, and other public materials using legal, login-free, source-traceable evidence. Use when a coding or product decision needs public research while keeping RESEARCH, CANDIDATE, DECISION, and IMPLEMENTATION as separate stages.
skills/safe-public-research/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.